Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/29365
Title: Sensitivity analysis of multilayer perceptron to input perturbation
Authors: Zeng, X
Yeung, DS
Sun, XQ
Keywords: Error analysis
Feedforward neural nets
Multilayer perceptrons
Perturbation techniques
Sensitivity analysis
Issue Date: 2000
Publisher: IEEE
Source: 2000 IEEE International Conference on Systems, Man, and Cybernetics, October 2000, Nashville, TN, v. 4, p. 2509-2514 How to cite?
Abstract: An important issue in the design and implementation of neural networks is the sensitivity of neural network output to parameter perturbations. Past research in this area has focused on network sensitivity analysis after training. Very few research projects have considered sensitivity analysis as a design issue prior to network implementation. The authors discuss the sensitivity of the most popular and general feedforward networks (multilayer perceptron (MLP)) to its input perturbation. The sensitivity is defined as the mathematical expectation of output errors of the MLP arising from input error with respect to all input and weight values in a given continuous interval. The sensitivity for a single neuron is discussed first, and an analytical expression that is a function of the input error is approximately derived. Then an algorithm is given to compute the sensitivity for an entire MLP network. The theoretical results of the derived formula were shown to agree with experimental results. By analyzing the derived analytical expression and implementing the given algorithm on a number of representative MLP networks, some significant observations on the behavior of sensitivity are discovered, which could be useful for network design consideration
URI: http://hdl.handle.net/10397/29365
ISBN: 0-7803-6583-6
ISSN: 1062-922X
DOI: 10.1109/ICSMC.2000.884370
Appears in Collections:Conference Paper

Access
View full-text via PolyU eLinks SFX Query
Show full item record

Page view(s)

32
Last Week
2
Last month
Checked on Aug 13, 2017

Google ScholarTM

Check

Altmetric



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.